/On the Dimensionality of Deformable Face Models

On the Dimensionality of Deformable Face Models

Iain Matthews, Jing Xiao and Simon Baker
Tech. Report, CMU-RI-TR-06-12, Robotics Institute, Carnegie Mellon University, March, 2006

Download Publication (PDF)

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.


Model-based face analysis is a general paradigm with applications that include face recognition, expression recognition, lipreading, head pose estimation, and gaze estimation. A face model is first constructed from a collection of training data, either 2D images or 3D range scans. The face model is then fit to the input image(s) and the model parameters used in whatever the application is. Most existing face models can be classified as either 2D (e.g. Active Appearance Models) or 3D (e.g. Morphable Models.) In this paper we compare 2D and 3D face models along four axes: (1) representational power, (2) construction, (3) real-time fitting, and (4) self occlusion reasoning. For each axis in turn, we outline the differences that result from using a 2D or a 3D face model.

BibTeX Reference
author = {Iain Matthews and Jing Xiao and Simon Baker},
title = {On the Dimensionality of Deformable Face Models},
year = {2006},
month = {March},
institution = {Carnegie Mellon University},
address = {Pittsburgh, PA},
number = {CMU-RI-TR-06-12},
keywords = {Model-based face analysis, 2D Active AppearanceModels, 3D Morphable Models, representational power, modelconstruction, non-rigid structure-from-motion, factorization,real-time fitting, the inverse compositional algorithm, constrainedfitting, occlusion reasoning},